© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123474
    Prev
    Next
    INDEX
    Explanations

    indefinite article followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens—quantities, measures, or other numbers (including decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -2.34
    まさかの
    -1.68
    マジで
    -1.67
     inteligentes
    -1.63
    レンタ
    -1.60
    私に
    -1.59
     acontecimientos
    -1.58
    ]
    -1.56
    僕も
    -1.56
     douleur
    -1.55
    POSITIVE LOGITS
     for
    1.83
     from
    1.77
     with
    1.66
     recevrez
    1.49
    ”,
    1.48
    捺
    1.46
     они
    1.45
     They
    1.43
    ėms
    1.40
    preneurs
    1.38
    Activations Density 0.008%

    No Known Activations